Modeling Multivariate Distributions Using Copulas: Applications in Marketing

Danaher, Peter J.; Smith, Michael S.
January 2011
Marketing Science;Jan/Feb2011, Vol. 30 Issue 1, p4
Academic Journal
In this research we introduce a new class of multivariate probability models to the marketing literature. Known as "copula models," they have a number of attractive features. First, they permit the combination of any univariate marginal distributions that need not come from the same distributional family. Second, a particular class of copula models, called "elliptical copula," has the property that they increase in complexity at a much slower rate than existing multivariate probability models as the number of dimensions increase. Third, they are very general, encompassing a number of existing multivariate models and providing a framework for generating many more. These advantages give copula models a greater potential for use in empirical analysis than existing probability models used in marketing. We exploit and extend recent developments in Bayesian estimation to propose an approach that allows reliable estimation of elliptical copula models in high dimensions. Rather than focusing on a single marketing problem, we demonstrate the versatility and accuracy of copula models with four examples to show the flexibility of the method. In every case, the copula model either handles a situation that could not be modeled previously or gives improved accuracy compared with prior models.


Related Articles

  • Bayesian Separation of Non-Stationary Mixtures of Dependent Gaussian Sources. Gençağa, Deniz; Kuruoğlu, Ercan E.; Ertüzün, Ayşın // AIP Conference Proceedings;2005, Vol. 803 Issue 1, p257 

    In this work, we propose a novel approach to perform Dependent Component Analysis (DCA). DCA can be thought as the separation of latent, dependent sources from their observed mixtures which is a more realistic model than Independent Component Analysis (ICA) where the sources are assumed to be...

  • Estimation Issues for Copulas Applied to Marketing Data. Danaher, Peter J.; Smith, Michael S. // Marketing Science;Jan/Feb2011, Vol. 30 Issue 1, p25 

    Estimating copula models using Bayesian methods presents some subtle challenges, ranging from specification of the prior to computational tractability. There is also some debate about what is the most appropriate copula to employ from those available. We address these issues here and conclude by...

  • Constructing Multivariate Distributions with Generalized Marginals And t-Copulas. Dass, Sarat C.; Wenmei Huang; Muthuvalu, Mohana S. // AIP Conference Proceedings;2014, Vol. 1621, p435 

    Generalized distributions are probability distributions that have both discrete and continuous components. In this paper, a method is proposed for constructing flexible multivariate distributions based on arbitrarily pre-specified generalized marginals and t-copulas. We give theoretical results...

  • Robust Gaussian Process Regression with a Student-t Likelihood. Jylänki, Pasi; Vanhatalo, Jarno; Vehtari, Aki // Journal of Machine Learning Research;Nov2011, Vol. 12 Issue 11, p3227 

    This paper considers the robust and efficient implementation of Gaussian process regression with a Student-t observation model, which has a non-log-concave likelihood. The challenge with the Student-t model is the analytically intractable inference which is why several approximative methods have...

  • A Bayesian two-level model for fluctuation assay. Zheng, Qi // Genetica;Nov2011, Vol. 139 Issue 11/12, p1409 

    The fluctuation experiment is an essential tool for measuring microbial mutation rates in the laboratory. When inferring the mutation rate from an experiment, one assumes that the number of mutants in each test tube follows a common distribution. This assumption conceptually restricts the scope...

  • Bayesian model selection for partially observed diffusion models. Dellaportas, Petros; Friel, Nial; Roberts, Gareth O. // Biometrika;Dec2006, Vol. 93 Issue 4, p809 

    We present an approach to Bayesian model selection for finitely observed diffusion processes. We use data augmentation by treating the paths between observed points as missing data. For a fixed model formulation, the strong dependence between the missing paths and the volatility of the diffusion...

  • Alternatives To The MCMC Method. Knüsel, Leo // AIP Conference Proceedings;2004, Vol. 735 Issue 1, p387 

    The Markov Chain Monte Carlo method (MCMC) is often used to generate independent (pseudo) random numbers from a distribution with a density that is known only up to a normalizing constant. With the MCMC method it is not necessary to compute the normalizing constant. In this paper we show that...

  • Markov chain Monte Carlo model determination for hierarchical and graphical log-linear models. Dellaportas, Petros; Forster, Jonathan J. // Biometrika;Sep1999, Vol. 86 Issue 3, p615 

    We use reversible jump Markov chain Monte Carlo methods (Green, 1995) to develop strategies for calculating posterior probabilities of hierarchical, graphical or decomposable log-linear models for high-dimensional contingency tables. Even for tables of moderate size, these sets of models may be...

  • Bayesian comparison of different rainfall depth–duration–frequency relationships. Muller, Aurélie; Bacro, Jean-Noël; Lang, Michel // Stochastic Environmental Research & Risk Assessment;Jan2008, Vol. 22 Issue 1, p33 

    Depth–duration–frequency curves estimate the rainfall intensity patterns for various return periods and rainfall durations. An empirical model based on the generalized extreme value distribution is presented for hourly maximum rainfall, and improved by the inclusion of daily...


Read the Article


Sorry, but this item is not currently available from your library.

Try another library?
Sign out of this library

Other Topics